Talking to Machines: do you read me?
This is an incremental review of the author's contributions to dialogue systems research, primarily for academic and industrial audiences.
The dissertation reviews the author's career research on dialogue systems, covering modular architectures, end-to-end deep neural networks, and recent work on task-oriented dialogues and conversational QA, with a focus on large language models for task-oriented and multimodal dialogues.
In this dissertation I would like to guide the reader to the research on dialogue but more precisely the research I have conducted during my career since my PhD thesis. Starting from modular architectures with machine learning/deep learning and reinforcement learning to end-to-end deep neural networks. Besides my work as research associate, I also present the work I have supervised in the last years. I review briefly the state of the art and highlight the open research problems on conversational agents. Afterwards, I present my contribution to Task-Oriented Dialogues (TOD), both as research associate and as the industrial supervisor of CIFRE theses. I discuss conversational QA. Particularly, I present the work of two PhD candidates Thibault Cordier and Sebastien Montella; as well as the work of the young researcher Quentin Brabant. Finally, I present the scientific project, where I discuss about Large Language Models (LLMs) for Task-Oriented Dialogue and Multimodal Task-Oriented Dialogue.